{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9998787339827803, "eval_steps": 500, "global_step": 7730, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002587008367355188, "grad_norm": 3.117795467376709, "learning_rate": 8.624407072013799e-08, "loss": 3.7293, "step": 20 }, { "epoch": 0.005174016734710376, "grad_norm": 3.1848440170288086, "learning_rate": 1.7248814144027598e-07, "loss": 3.7345, "step": 40 }, { "epoch": 0.007761025102065565, "grad_norm": 3.073965072631836, "learning_rate": 2.5873221216041403e-07, "loss": 3.7232, "step": 60 }, { "epoch": 0.010348033469420752, "grad_norm": 2.366281032562256, "learning_rate": 3.4497628288055197e-07, "loss": 3.6733, "step": 80 }, { "epoch": 0.012935041836775941, "grad_norm": 1.8071706295013428, "learning_rate": 4.3122035360069e-07, "loss": 3.5801, "step": 100 }, { "epoch": 0.01552205020413113, "grad_norm": 1.3455595970153809, "learning_rate": 5.174644243208281e-07, "loss": 3.4895, "step": 120 }, { "epoch": 0.018109058571486317, "grad_norm": 0.9497399926185608, "learning_rate": 6.03708495040966e-07, "loss": 3.3785, "step": 140 }, { "epoch": 0.020696066938841504, "grad_norm": 0.9015834331512451, "learning_rate": 6.899525657611039e-07, "loss": 3.3095, "step": 160 }, { "epoch": 0.023283075306196693, "grad_norm": 0.8537250757217407, "learning_rate": 7.761966364812419e-07, "loss": 3.1901, "step": 180 }, { "epoch": 0.025870083673551883, "grad_norm": 0.8126162886619568, "learning_rate": 8.6244070720138e-07, "loss": 3.1323, "step": 200 }, { "epoch": 0.02845709204090707, "grad_norm": 0.8042150139808655, "learning_rate": 9.48684777921518e-07, "loss": 3.0969, "step": 220 }, { "epoch": 0.03104410040826226, "grad_norm": 0.7180504202842712, "learning_rate": 1.0349288486416561e-06, "loss": 3.0284, "step": 240 }, { "epoch": 0.033631108775617445, "grad_norm": 0.7540543675422668, "learning_rate": 1.1211729193617941e-06, "loss": 3.043, "step": 260 }, { "epoch": 0.036218117142972635, "grad_norm": 0.720626175403595, "learning_rate": 1.207416990081932e-06, "loss": 3.002, "step": 280 }, { "epoch": 0.038805125510327824, "grad_norm": 0.761584997177124, "learning_rate": 1.29366106080207e-06, "loss": 3.0019, "step": 300 }, { "epoch": 0.04139213387768301, "grad_norm": 0.7120524644851685, "learning_rate": 1.3799051315222079e-06, "loss": 2.9614, "step": 320 }, { "epoch": 0.0439791422450382, "grad_norm": 0.6938987374305725, "learning_rate": 1.4661492022423459e-06, "loss": 2.9435, "step": 340 }, { "epoch": 0.04656615061239339, "grad_norm": 0.7532190680503845, "learning_rate": 1.5523932729624839e-06, "loss": 2.9194, "step": 360 }, { "epoch": 0.049153158979748576, "grad_norm": 0.7144018411636353, "learning_rate": 1.6386373436826219e-06, "loss": 2.909, "step": 380 }, { "epoch": 0.051740167347103766, "grad_norm": 0.7019342184066772, "learning_rate": 1.72488141440276e-06, "loss": 2.8771, "step": 400 }, { "epoch": 0.05432717571445895, "grad_norm": 0.7003944516181946, "learning_rate": 1.8111254851228978e-06, "loss": 2.892, "step": 420 }, { "epoch": 0.05691418408181414, "grad_norm": 0.7309603095054626, "learning_rate": 1.897369555843036e-06, "loss": 2.8603, "step": 440 }, { "epoch": 0.05950119244916933, "grad_norm": 0.6825790405273438, "learning_rate": 1.983613626563174e-06, "loss": 2.8596, "step": 460 }, { "epoch": 0.06208820081652452, "grad_norm": 0.6874191164970398, "learning_rate": 2.0698576972833122e-06, "loss": 2.8482, "step": 480 }, { "epoch": 0.0646752091838797, "grad_norm": 0.7430766224861145, "learning_rate": 2.15610176800345e-06, "loss": 2.8446, "step": 500 }, { "epoch": 0.06726221755123489, "grad_norm": 0.7108047008514404, "learning_rate": 2.2423458387235882e-06, "loss": 2.828, "step": 520 }, { "epoch": 0.06984922591859008, "grad_norm": 0.7121191620826721, "learning_rate": 2.328589909443726e-06, "loss": 2.8002, "step": 540 }, { "epoch": 0.07243623428594527, "grad_norm": 0.7068054676055908, "learning_rate": 2.414833980163864e-06, "loss": 2.8119, "step": 560 }, { "epoch": 0.07502324265330046, "grad_norm": 0.6924973726272583, "learning_rate": 2.501078050884002e-06, "loss": 2.7846, "step": 580 }, { "epoch": 0.07761025102065565, "grad_norm": 0.7206343412399292, "learning_rate": 2.58732212160414e-06, "loss": 2.7896, "step": 600 }, { "epoch": 0.08019725938801084, "grad_norm": 0.7203959822654724, "learning_rate": 2.673566192324278e-06, "loss": 2.7793, "step": 620 }, { "epoch": 0.08278426775536601, "grad_norm": 0.7108203172683716, "learning_rate": 2.7598102630444157e-06, "loss": 2.7642, "step": 640 }, { "epoch": 0.0853712761227212, "grad_norm": 0.7053371667861938, "learning_rate": 2.846054333764554e-06, "loss": 2.7588, "step": 660 }, { "epoch": 0.0879582844900764, "grad_norm": 0.6986986398696899, "learning_rate": 2.9322984044846917e-06, "loss": 2.7453, "step": 680 }, { "epoch": 0.09054529285743158, "grad_norm": 0.7130378484725952, "learning_rate": 3.01854247520483e-06, "loss": 2.7249, "step": 700 }, { "epoch": 0.09313230122478677, "grad_norm": 0.7068546414375305, "learning_rate": 3.1047865459249677e-06, "loss": 2.7134, "step": 720 }, { "epoch": 0.09571930959214196, "grad_norm": 0.7224396467208862, "learning_rate": 3.191030616645106e-06, "loss": 2.718, "step": 740 }, { "epoch": 0.09830631795949715, "grad_norm": 0.7299512624740601, "learning_rate": 3.2772746873652437e-06, "loss": 2.7049, "step": 760 }, { "epoch": 0.10089332632685234, "grad_norm": 0.7126713991165161, "learning_rate": 3.363518758085382e-06, "loss": 2.7199, "step": 780 }, { "epoch": 0.10348033469420753, "grad_norm": 0.6644526720046997, "learning_rate": 3.44976282880552e-06, "loss": 2.7046, "step": 800 }, { "epoch": 0.10606734306156272, "grad_norm": 0.7410451769828796, "learning_rate": 3.536006899525658e-06, "loss": 2.7012, "step": 820 }, { "epoch": 0.1086543514289179, "grad_norm": 0.7218043208122253, "learning_rate": 3.6222509702457957e-06, "loss": 2.71, "step": 840 }, { "epoch": 0.11124135979627309, "grad_norm": 0.6941894292831421, "learning_rate": 3.708495040965934e-06, "loss": 2.7035, "step": 860 }, { "epoch": 0.11382836816362828, "grad_norm": 0.6824482679367065, "learning_rate": 3.794739111686072e-06, "loss": 2.6741, "step": 880 }, { "epoch": 0.11641537653098347, "grad_norm": 0.7253878712654114, "learning_rate": 3.88098318240621e-06, "loss": 2.6831, "step": 900 }, { "epoch": 0.11900238489833866, "grad_norm": 0.6949134469032288, "learning_rate": 3.967227253126348e-06, "loss": 2.6674, "step": 920 }, { "epoch": 0.12158939326569385, "grad_norm": 0.7096832394599915, "learning_rate": 4.053471323846485e-06, "loss": 2.674, "step": 940 }, { "epoch": 0.12417640163304904, "grad_norm": 0.6938119530677795, "learning_rate": 4.1397153945666245e-06, "loss": 2.6533, "step": 960 }, { "epoch": 0.12676341000040423, "grad_norm": 0.6781166195869446, "learning_rate": 4.225959465286762e-06, "loss": 2.6426, "step": 980 }, { "epoch": 0.1293504183677594, "grad_norm": 0.7600920796394348, "learning_rate": 4.3122035360069e-06, "loss": 2.6454, "step": 1000 }, { "epoch": 0.1319374267351146, "grad_norm": 0.6884315609931946, "learning_rate": 4.398447606727037e-06, "loss": 2.6324, "step": 1020 }, { "epoch": 0.13452443510246978, "grad_norm": 0.7092069387435913, "learning_rate": 4.4846916774471764e-06, "loss": 2.6181, "step": 1040 }, { "epoch": 0.13711144346982498, "grad_norm": 0.729020357131958, "learning_rate": 4.570935748167314e-06, "loss": 2.6217, "step": 1060 }, { "epoch": 0.13969845183718016, "grad_norm": 0.7104108333587646, "learning_rate": 4.657179818887452e-06, "loss": 2.6152, "step": 1080 }, { "epoch": 0.14228546020453534, "grad_norm": 0.8092931509017944, "learning_rate": 4.743423889607589e-06, "loss": 2.621, "step": 1100 }, { "epoch": 0.14487246857189054, "grad_norm": 0.6620950102806091, "learning_rate": 4.829667960327728e-06, "loss": 2.6166, "step": 1120 }, { "epoch": 0.14745947693924571, "grad_norm": 0.6813467741012573, "learning_rate": 4.915912031047866e-06, "loss": 2.6171, "step": 1140 }, { "epoch": 0.15004648530660092, "grad_norm": 0.7140293121337891, "learning_rate": 5.002156101768004e-06, "loss": 2.5911, "step": 1160 }, { "epoch": 0.1526334936739561, "grad_norm": 0.7278040051460266, "learning_rate": 5.088400172488141e-06, "loss": 2.6055, "step": 1180 }, { "epoch": 0.1552205020413113, "grad_norm": 0.7283148169517517, "learning_rate": 5.17464424320828e-06, "loss": 2.6054, "step": 1200 }, { "epoch": 0.15780751040866647, "grad_norm": 0.7109535932540894, "learning_rate": 5.260888313928419e-06, "loss": 2.56, "step": 1220 }, { "epoch": 0.16039451877602168, "grad_norm": 0.7203260064125061, "learning_rate": 5.347132384648556e-06, "loss": 2.578, "step": 1240 }, { "epoch": 0.16298152714337685, "grad_norm": 0.7385180592536926, "learning_rate": 5.433376455368694e-06, "loss": 2.5829, "step": 1260 }, { "epoch": 0.16556853551073203, "grad_norm": 0.7511777281761169, "learning_rate": 5.5196205260888315e-06, "loss": 2.5703, "step": 1280 }, { "epoch": 0.16815554387808723, "grad_norm": 0.7461130619049072, "learning_rate": 5.60586459680897e-06, "loss": 2.5891, "step": 1300 }, { "epoch": 0.1707425522454424, "grad_norm": 0.7192751169204712, "learning_rate": 5.692108667529108e-06, "loss": 2.552, "step": 1320 }, { "epoch": 0.1733295606127976, "grad_norm": 0.7672246694564819, "learning_rate": 5.778352738249245e-06, "loss": 2.5451, "step": 1340 }, { "epoch": 0.1759165689801528, "grad_norm": 0.8286859393119812, "learning_rate": 5.8645968089693835e-06, "loss": 2.5691, "step": 1360 }, { "epoch": 0.178503577347508, "grad_norm": 0.8903458714485168, "learning_rate": 5.9508408796895225e-06, "loss": 2.5717, "step": 1380 }, { "epoch": 0.18109058571486317, "grad_norm": 0.7192072868347168, "learning_rate": 6.03708495040966e-06, "loss": 2.547, "step": 1400 }, { "epoch": 0.18367759408221837, "grad_norm": 0.7470182776451111, "learning_rate": 6.123329021129798e-06, "loss": 2.5309, "step": 1420 }, { "epoch": 0.18626460244957355, "grad_norm": 0.7186440229415894, "learning_rate": 6.2095730918499354e-06, "loss": 2.5433, "step": 1440 }, { "epoch": 0.18885161081692872, "grad_norm": 0.7359221577644348, "learning_rate": 6.295817162570074e-06, "loss": 2.5482, "step": 1460 }, { "epoch": 0.19143861918428393, "grad_norm": 0.7859694957733154, "learning_rate": 6.382061233290212e-06, "loss": 2.5371, "step": 1480 }, { "epoch": 0.1940256275516391, "grad_norm": 0.7339861392974854, "learning_rate": 6.468305304010349e-06, "loss": 2.5217, "step": 1500 }, { "epoch": 0.1966126359189943, "grad_norm": 0.7527260780334473, "learning_rate": 6.554549374730487e-06, "loss": 2.5183, "step": 1520 }, { "epoch": 0.19919964428634948, "grad_norm": 0.7345518469810486, "learning_rate": 6.6407934454506265e-06, "loss": 2.5249, "step": 1540 }, { "epoch": 0.20178665265370468, "grad_norm": 0.736298680305481, "learning_rate": 6.727037516170764e-06, "loss": 2.5184, "step": 1560 }, { "epoch": 0.20437366102105986, "grad_norm": 0.7677698135375977, "learning_rate": 6.813281586890902e-06, "loss": 2.5134, "step": 1580 }, { "epoch": 0.20696066938841506, "grad_norm": 0.7627900838851929, "learning_rate": 6.89952565761104e-06, "loss": 2.5064, "step": 1600 }, { "epoch": 0.20954767775577024, "grad_norm": 0.7290985584259033, "learning_rate": 6.985769728331178e-06, "loss": 2.5124, "step": 1620 }, { "epoch": 0.21213468612312544, "grad_norm": 0.7347148060798645, "learning_rate": 7.072013799051316e-06, "loss": 2.4901, "step": 1640 }, { "epoch": 0.21472169449048062, "grad_norm": 0.7257357239723206, "learning_rate": 7.158257869771453e-06, "loss": 2.4884, "step": 1660 }, { "epoch": 0.2173087028578358, "grad_norm": 0.7803710699081421, "learning_rate": 7.244501940491591e-06, "loss": 2.4899, "step": 1680 }, { "epoch": 0.219895711225191, "grad_norm": 0.6987377405166626, "learning_rate": 7.33074601121173e-06, "loss": 2.5001, "step": 1700 }, { "epoch": 0.22248271959254617, "grad_norm": 0.6989637017250061, "learning_rate": 7.416990081931868e-06, "loss": 2.4941, "step": 1720 }, { "epoch": 0.22506972795990138, "grad_norm": 0.7391577363014221, "learning_rate": 7.503234152652006e-06, "loss": 2.4811, "step": 1740 }, { "epoch": 0.22765673632725655, "grad_norm": 0.7664337754249573, "learning_rate": 7.589478223372144e-06, "loss": 2.4806, "step": 1760 }, { "epoch": 0.23024374469461176, "grad_norm": 0.7150381207466125, "learning_rate": 7.675722294092282e-06, "loss": 2.4674, "step": 1780 }, { "epoch": 0.23283075306196693, "grad_norm": 0.7978541254997253, "learning_rate": 7.76196636481242e-06, "loss": 2.4633, "step": 1800 }, { "epoch": 0.23541776142932214, "grad_norm": 0.7218653559684753, "learning_rate": 7.848210435532557e-06, "loss": 2.4589, "step": 1820 }, { "epoch": 0.2380047697966773, "grad_norm": 0.723008930683136, "learning_rate": 7.934454506252696e-06, "loss": 2.467, "step": 1840 }, { "epoch": 0.2405917781640325, "grad_norm": 0.7375757098197937, "learning_rate": 8.020698576972833e-06, "loss": 2.4812, "step": 1860 }, { "epoch": 0.2431787865313877, "grad_norm": 0.7501986026763916, "learning_rate": 8.10694264769297e-06, "loss": 2.4587, "step": 1880 }, { "epoch": 0.24576579489874287, "grad_norm": 0.7394606471061707, "learning_rate": 8.19318671841311e-06, "loss": 2.4514, "step": 1900 }, { "epoch": 0.24835280326609807, "grad_norm": 0.7856109738349915, "learning_rate": 8.279430789133249e-06, "loss": 2.45, "step": 1920 }, { "epoch": 0.25093981163345325, "grad_norm": 0.7603466510772705, "learning_rate": 8.365674859853386e-06, "loss": 2.4341, "step": 1940 }, { "epoch": 0.25352682000080845, "grad_norm": 0.7223484516143799, "learning_rate": 8.451918930573524e-06, "loss": 2.4349, "step": 1960 }, { "epoch": 0.25611382836816365, "grad_norm": 0.7488518357276917, "learning_rate": 8.538163001293663e-06, "loss": 2.4417, "step": 1980 }, { "epoch": 0.2587008367355188, "grad_norm": 0.83389812707901, "learning_rate": 8.6244070720138e-06, "loss": 2.4266, "step": 2000 }, { "epoch": 0.261287845102874, "grad_norm": 0.7574110627174377, "learning_rate": 8.710651142733937e-06, "loss": 2.4471, "step": 2020 }, { "epoch": 0.2638748534702292, "grad_norm": 0.7482550740242004, "learning_rate": 8.796895213454075e-06, "loss": 2.4368, "step": 2040 }, { "epoch": 0.26646186183758436, "grad_norm": 0.7341257333755493, "learning_rate": 8.883139284174214e-06, "loss": 2.4303, "step": 2060 }, { "epoch": 0.26904887020493956, "grad_norm": 0.764855682849884, "learning_rate": 8.969383354894353e-06, "loss": 2.4176, "step": 2080 }, { "epoch": 0.27163587857229476, "grad_norm": 0.7559799551963806, "learning_rate": 9.055627425614489e-06, "loss": 2.4088, "step": 2100 }, { "epoch": 0.27422288693964997, "grad_norm": 0.7435436844825745, "learning_rate": 9.141871496334628e-06, "loss": 2.4241, "step": 2120 }, { "epoch": 0.2768098953070051, "grad_norm": 0.7100109457969666, "learning_rate": 9.228115567054767e-06, "loss": 2.4122, "step": 2140 }, { "epoch": 0.2793969036743603, "grad_norm": 0.7357873320579529, "learning_rate": 9.314359637774904e-06, "loss": 2.425, "step": 2160 }, { "epoch": 0.2819839120417155, "grad_norm": 0.7281599640846252, "learning_rate": 9.400603708495041e-06, "loss": 2.4242, "step": 2180 }, { "epoch": 0.28457092040907067, "grad_norm": 0.7816882729530334, "learning_rate": 9.486847779215179e-06, "loss": 2.4115, "step": 2200 }, { "epoch": 0.2871579287764259, "grad_norm": 0.7402174472808838, "learning_rate": 9.573091849935318e-06, "loss": 2.4253, "step": 2220 }, { "epoch": 0.2897449371437811, "grad_norm": 0.7378434538841248, "learning_rate": 9.659335920655457e-06, "loss": 2.4015, "step": 2240 }, { "epoch": 0.2923319455111363, "grad_norm": 0.7792133688926697, "learning_rate": 9.745579991375592e-06, "loss": 2.3947, "step": 2260 }, { "epoch": 0.29491895387849143, "grad_norm": 0.7180085778236389, "learning_rate": 9.831824062095732e-06, "loss": 2.3975, "step": 2280 }, { "epoch": 0.29750596224584663, "grad_norm": 0.7536414861679077, "learning_rate": 9.91806813281587e-06, "loss": 2.4052, "step": 2300 }, { "epoch": 0.30009297061320184, "grad_norm": 0.7593511939048767, "learning_rate": 9.999999943356089e-06, "loss": 2.3856, "step": 2320 }, { "epoch": 0.30267997898055704, "grad_norm": 0.6879323720932007, "learning_rate": 9.999975020055695e-06, "loss": 2.4107, "step": 2340 }, { "epoch": 0.3052669873479122, "grad_norm": 0.7193155884742737, "learning_rate": 9.999904781886476e-06, "loss": 2.3872, "step": 2360 }, { "epoch": 0.3078539957152674, "grad_norm": 0.7621170282363892, "learning_rate": 9.999789229485002e-06, "loss": 2.3844, "step": 2380 }, { "epoch": 0.3104410040826226, "grad_norm": 0.7357332110404968, "learning_rate": 9.999628363898525e-06, "loss": 2.3863, "step": 2400 }, { "epoch": 0.31302801244997774, "grad_norm": 0.753011167049408, "learning_rate": 9.999422186584978e-06, "loss": 2.3807, "step": 2420 }, { "epoch": 0.31561502081733295, "grad_norm": 0.7547248005867004, "learning_rate": 9.999170699412942e-06, "loss": 2.3691, "step": 2440 }, { "epoch": 0.31820202918468815, "grad_norm": 0.7450150847434998, "learning_rate": 9.998873904661655e-06, "loss": 2.3495, "step": 2460 }, { "epoch": 0.32078903755204335, "grad_norm": 0.7460102438926697, "learning_rate": 9.998531805020974e-06, "loss": 2.3582, "step": 2480 }, { "epoch": 0.3233760459193985, "grad_norm": 0.7281093597412109, "learning_rate": 9.998144403591352e-06, "loss": 2.3559, "step": 2500 }, { "epoch": 0.3259630542867537, "grad_norm": 0.7635049223899841, "learning_rate": 9.99771170388382e-06, "loss": 2.3668, "step": 2520 }, { "epoch": 0.3285500626541089, "grad_norm": 0.7504300475120544, "learning_rate": 9.997233709819935e-06, "loss": 2.3642, "step": 2540 }, { "epoch": 0.33113707102146406, "grad_norm": 0.73244309425354, "learning_rate": 9.996710425731776e-06, "loss": 2.3634, "step": 2560 }, { "epoch": 0.33372407938881926, "grad_norm": 0.816100537776947, "learning_rate": 9.996141856361871e-06, "loss": 2.3405, "step": 2580 }, { "epoch": 0.33631108775617446, "grad_norm": 0.7125614285469055, "learning_rate": 9.995528006863175e-06, "loss": 2.3594, "step": 2600 }, { "epoch": 0.33889809612352967, "grad_norm": 0.7901700735092163, "learning_rate": 9.994868882799022e-06, "loss": 2.3636, "step": 2620 }, { "epoch": 0.3414851044908848, "grad_norm": 0.7499126195907593, "learning_rate": 9.994164490143062e-06, "loss": 2.36, "step": 2640 }, { "epoch": 0.34407211285824, "grad_norm": 0.78279048204422, "learning_rate": 9.99341483527922e-06, "loss": 2.3685, "step": 2660 }, { "epoch": 0.3466591212255952, "grad_norm": 0.7683995366096497, "learning_rate": 9.992619925001632e-06, "loss": 2.3532, "step": 2680 }, { "epoch": 0.3492461295929504, "grad_norm": 0.7231781482696533, "learning_rate": 9.991779766514586e-06, "loss": 2.377, "step": 2700 }, { "epoch": 0.3518331379603056, "grad_norm": 0.7408224940299988, "learning_rate": 9.990894367432453e-06, "loss": 2.3406, "step": 2720 }, { "epoch": 0.3544201463276608, "grad_norm": 0.7654145956039429, "learning_rate": 9.989963735779623e-06, "loss": 2.3627, "step": 2740 }, { "epoch": 0.357007154695016, "grad_norm": 0.7166858315467834, "learning_rate": 9.988987879990428e-06, "loss": 2.3343, "step": 2760 }, { "epoch": 0.35959416306237113, "grad_norm": 0.79310142993927, "learning_rate": 9.987966808909069e-06, "loss": 2.3521, "step": 2780 }, { "epoch": 0.36218117142972633, "grad_norm": 0.7726064324378967, "learning_rate": 9.98690053178953e-06, "loss": 2.3408, "step": 2800 }, { "epoch": 0.36476817979708154, "grad_norm": 0.7428059577941895, "learning_rate": 9.985789058295501e-06, "loss": 2.3238, "step": 2820 }, { "epoch": 0.36735518816443674, "grad_norm": 0.7808260321617126, "learning_rate": 9.984632398500289e-06, "loss": 2.3164, "step": 2840 }, { "epoch": 0.3699421965317919, "grad_norm": 0.7835705280303955, "learning_rate": 9.983430562886723e-06, "loss": 2.343, "step": 2860 }, { "epoch": 0.3725292048991471, "grad_norm": 0.7703275680541992, "learning_rate": 9.982183562347063e-06, "loss": 2.3354, "step": 2880 }, { "epoch": 0.3751162132665023, "grad_norm": 0.7307262420654297, "learning_rate": 9.980891408182897e-06, "loss": 2.3445, "step": 2900 }, { "epoch": 0.37770322163385744, "grad_norm": 0.6830443143844604, "learning_rate": 9.979554112105045e-06, "loss": 2.3437, "step": 2920 }, { "epoch": 0.38029023000121265, "grad_norm": 0.7646154761314392, "learning_rate": 9.978171686233445e-06, "loss": 2.3316, "step": 2940 }, { "epoch": 0.38287723836856785, "grad_norm": 0.7598294615745544, "learning_rate": 9.97674414309705e-06, "loss": 2.3135, "step": 2960 }, { "epoch": 0.38546424673592306, "grad_norm": 0.7368634343147278, "learning_rate": 9.975271495633709e-06, "loss": 2.3189, "step": 2980 }, { "epoch": 0.3880512551032782, "grad_norm": 0.7349269390106201, "learning_rate": 9.973753757190057e-06, "loss": 2.307, "step": 3000 }, { "epoch": 0.3906382634706334, "grad_norm": 0.7512723803520203, "learning_rate": 9.972190941521382e-06, "loss": 2.3195, "step": 3020 }, { "epoch": 0.3932252718379886, "grad_norm": 0.7430227398872375, "learning_rate": 9.970583062791517e-06, "loss": 2.3087, "step": 3040 }, { "epoch": 0.3958122802053438, "grad_norm": 0.7576317191123962, "learning_rate": 9.968930135572694e-06, "loss": 2.3, "step": 3060 }, { "epoch": 0.39839928857269896, "grad_norm": 0.7394402623176575, "learning_rate": 9.967232174845426e-06, "loss": 2.3164, "step": 3080 }, { "epoch": 0.40098629694005417, "grad_norm": 0.7061188220977783, "learning_rate": 9.965489195998363e-06, "loss": 2.3187, "step": 3100 }, { "epoch": 0.40357330530740937, "grad_norm": 0.7332024574279785, "learning_rate": 9.963701214828154e-06, "loss": 2.3085, "step": 3120 }, { "epoch": 0.4061603136747645, "grad_norm": 0.663925051689148, "learning_rate": 9.961868247539308e-06, "loss": 2.2978, "step": 3140 }, { "epoch": 0.4087473220421197, "grad_norm": 0.7256314158439636, "learning_rate": 9.959990310744042e-06, "loss": 2.3209, "step": 3160 }, { "epoch": 0.4113343304094749, "grad_norm": 0.711919903755188, "learning_rate": 9.958067421462133e-06, "loss": 2.3041, "step": 3180 }, { "epoch": 0.41392133877683013, "grad_norm": 0.714450478553772, "learning_rate": 9.956099597120762e-06, "loss": 2.2789, "step": 3200 }, { "epoch": 0.4165083471441853, "grad_norm": 0.7216628193855286, "learning_rate": 9.95408685555436e-06, "loss": 2.3056, "step": 3220 }, { "epoch": 0.4190953555115405, "grad_norm": 0.6629658341407776, "learning_rate": 9.952029215004441e-06, "loss": 2.3001, "step": 3240 }, { "epoch": 0.4216823638788957, "grad_norm": 0.8131959438323975, "learning_rate": 9.949926694119443e-06, "loss": 2.2881, "step": 3260 }, { "epoch": 0.4242693722462509, "grad_norm": 0.7133468389511108, "learning_rate": 9.94777931195455e-06, "loss": 2.2902, "step": 3280 }, { "epoch": 0.42685638061360603, "grad_norm": 0.7825130224227905, "learning_rate": 9.945587087971529e-06, "loss": 2.2829, "step": 3300 }, { "epoch": 0.42944338898096124, "grad_norm": 0.6878073811531067, "learning_rate": 9.943350042038545e-06, "loss": 2.2844, "step": 3320 }, { "epoch": 0.43203039734831644, "grad_norm": 0.7324455976486206, "learning_rate": 9.941068194429992e-06, "loss": 2.2932, "step": 3340 }, { "epoch": 0.4346174057156716, "grad_norm": 0.7330353856086731, "learning_rate": 9.938741565826295e-06, "loss": 2.2611, "step": 3360 }, { "epoch": 0.4372044140830268, "grad_norm": 0.8474377393722534, "learning_rate": 9.936370177313737e-06, "loss": 2.2938, "step": 3380 }, { "epoch": 0.439791422450382, "grad_norm": 0.776228666305542, "learning_rate": 9.933954050384253e-06, "loss": 2.292, "step": 3400 }, { "epoch": 0.4423784308177372, "grad_norm": 0.7257934212684631, "learning_rate": 9.931493206935249e-06, "loss": 2.2964, "step": 3420 }, { "epoch": 0.44496543918509235, "grad_norm": 0.7738561034202576, "learning_rate": 9.928987669269397e-06, "loss": 2.2585, "step": 3440 }, { "epoch": 0.44755244755244755, "grad_norm": 0.6888708472251892, "learning_rate": 9.926437460094431e-06, "loss": 2.281, "step": 3460 }, { "epoch": 0.45013945591980276, "grad_norm": 0.7120715975761414, "learning_rate": 9.923842602522948e-06, "loss": 2.2861, "step": 3480 }, { "epoch": 0.4527264642871579, "grad_norm": 0.770353376865387, "learning_rate": 9.92120312007219e-06, "loss": 2.271, "step": 3500 }, { "epoch": 0.4553134726545131, "grad_norm": 0.753852367401123, "learning_rate": 9.918519036663835e-06, "loss": 2.2592, "step": 3520 }, { "epoch": 0.4579004810218683, "grad_norm": 0.7479904294013977, "learning_rate": 9.915790376623785e-06, "loss": 2.2691, "step": 3540 }, { "epoch": 0.4604874893892235, "grad_norm": 0.7162041068077087, "learning_rate": 9.913017164681936e-06, "loss": 2.2637, "step": 3560 }, { "epoch": 0.46307449775657866, "grad_norm": 0.6859399080276489, "learning_rate": 9.91019942597196e-06, "loss": 2.2424, "step": 3580 }, { "epoch": 0.46566150612393387, "grad_norm": 0.7681860327720642, "learning_rate": 9.907337186031078e-06, "loss": 2.2758, "step": 3600 }, { "epoch": 0.46824851449128907, "grad_norm": 0.7416828274726868, "learning_rate": 9.904430470799826e-06, "loss": 2.2715, "step": 3620 }, { "epoch": 0.4708355228586443, "grad_norm": 0.7957201600074768, "learning_rate": 9.901479306621818e-06, "loss": 2.277, "step": 3640 }, { "epoch": 0.4734225312259994, "grad_norm": 0.71152663230896, "learning_rate": 9.89848372024351e-06, "loss": 2.2831, "step": 3660 }, { "epoch": 0.4760095395933546, "grad_norm": 0.6950436234474182, "learning_rate": 9.89544373881396e-06, "loss": 2.2678, "step": 3680 }, { "epoch": 0.47859654796070983, "grad_norm": 0.7226356267929077, "learning_rate": 9.89235938988458e-06, "loss": 2.2549, "step": 3700 }, { "epoch": 0.481183556328065, "grad_norm": 0.7032837867736816, "learning_rate": 9.88923070140888e-06, "loss": 2.2669, "step": 3720 }, { "epoch": 0.4837705646954202, "grad_norm": 0.749229371547699, "learning_rate": 9.886057701742222e-06, "loss": 2.2421, "step": 3740 }, { "epoch": 0.4863575730627754, "grad_norm": 0.7166919112205505, "learning_rate": 9.882840419641566e-06, "loss": 2.245, "step": 3760 }, { "epoch": 0.4889445814301306, "grad_norm": 0.7276502847671509, "learning_rate": 9.879578884265198e-06, "loss": 2.2542, "step": 3780 }, { "epoch": 0.49153158979748574, "grad_norm": 0.7321860194206238, "learning_rate": 9.876273125172476e-06, "loss": 2.2395, "step": 3800 }, { "epoch": 0.49411859816484094, "grad_norm": 0.6959764361381531, "learning_rate": 9.872923172323559e-06, "loss": 2.2588, "step": 3820 }, { "epoch": 0.49670560653219614, "grad_norm": 0.7237563729286194, "learning_rate": 9.869529056079133e-06, "loss": 2.2463, "step": 3840 }, { "epoch": 0.4992926148995513, "grad_norm": 0.7536144256591797, "learning_rate": 9.866090807200135e-06, "loss": 2.2394, "step": 3860 }, { "epoch": 0.5018796232669065, "grad_norm": 0.6835715770721436, "learning_rate": 9.862608456847484e-06, "loss": 2.2447, "step": 3880 }, { "epoch": 0.5044666316342616, "grad_norm": 0.7627236247062683, "learning_rate": 9.859082036581787e-06, "loss": 2.2727, "step": 3900 }, { "epoch": 0.5070536400016169, "grad_norm": 0.7260853052139282, "learning_rate": 9.855511578363057e-06, "loss": 2.2373, "step": 3920 }, { "epoch": 0.509640648368972, "grad_norm": 0.7366577386856079, "learning_rate": 9.851897114550423e-06, "loss": 2.2583, "step": 3940 }, { "epoch": 0.5122276567363273, "grad_norm": 0.718189001083374, "learning_rate": 9.848238677901844e-06, "loss": 2.2376, "step": 3960 }, { "epoch": 0.5148146651036825, "grad_norm": 0.6988586783409119, "learning_rate": 9.844536301573798e-06, "loss": 2.2413, "step": 3980 }, { "epoch": 0.5174016734710376, "grad_norm": 0.752648115158081, "learning_rate": 9.840790019120993e-06, "loss": 2.2346, "step": 4000 }, { "epoch": 0.5199886818383929, "grad_norm": 0.8000548481941223, "learning_rate": 9.836999864496058e-06, "loss": 2.2365, "step": 4020 }, { "epoch": 0.522575690205748, "grad_norm": 0.7324941158294678, "learning_rate": 9.833165872049235e-06, "loss": 2.2294, "step": 4040 }, { "epoch": 0.5251626985731032, "grad_norm": 0.765869140625, "learning_rate": 9.829288076528071e-06, "loss": 2.2418, "step": 4060 }, { "epoch": 0.5277497069404584, "grad_norm": 0.7222108244895935, "learning_rate": 9.825366513077104e-06, "loss": 2.2292, "step": 4080 }, { "epoch": 0.5303367153078136, "grad_norm": 0.7359380722045898, "learning_rate": 9.821401217237535e-06, "loss": 2.2491, "step": 4100 }, { "epoch": 0.5329237236751687, "grad_norm": 0.7288945317268372, "learning_rate": 9.817392224946916e-06, "loss": 2.2404, "step": 4120 }, { "epoch": 0.535510732042524, "grad_norm": 0.7518214583396912, "learning_rate": 9.813339572538822e-06, "loss": 2.2381, "step": 4140 }, { "epoch": 0.5380977404098791, "grad_norm": 0.753818154335022, "learning_rate": 9.809243296742516e-06, "loss": 2.2236, "step": 4160 }, { "epoch": 0.5406847487772344, "grad_norm": 0.7281918525695801, "learning_rate": 9.805103434682628e-06, "loss": 2.2142, "step": 4180 }, { "epoch": 0.5432717571445895, "grad_norm": 0.7605194449424744, "learning_rate": 9.800920023878803e-06, "loss": 2.2326, "step": 4200 }, { "epoch": 0.5458587655119447, "grad_norm": 0.7266237139701843, "learning_rate": 9.796693102245376e-06, "loss": 2.2144, "step": 4220 }, { "epoch": 0.5484457738792999, "grad_norm": 0.7575150728225708, "learning_rate": 9.792422708091014e-06, "loss": 2.2282, "step": 4240 }, { "epoch": 0.5510327822466551, "grad_norm": 0.7097237706184387, "learning_rate": 9.788108880118383e-06, "loss": 2.2139, "step": 4260 }, { "epoch": 0.5536197906140102, "grad_norm": 0.7074447870254517, "learning_rate": 9.783751657423787e-06, "loss": 2.2169, "step": 4280 }, { "epoch": 0.5562067989813655, "grad_norm": 0.7193735241889954, "learning_rate": 9.779351079496821e-06, "loss": 2.2435, "step": 4300 }, { "epoch": 0.5587938073487206, "grad_norm": 0.7104501128196716, "learning_rate": 9.774907186220005e-06, "loss": 2.198, "step": 4320 }, { "epoch": 0.5613808157160758, "grad_norm": 0.6711876392364502, "learning_rate": 9.770420017868426e-06, "loss": 2.1927, "step": 4340 }, { "epoch": 0.563967824083431, "grad_norm": 0.7272083163261414, "learning_rate": 9.765889615109379e-06, "loss": 2.2437, "step": 4360 }, { "epoch": 0.5665548324507862, "grad_norm": 0.7311263680458069, "learning_rate": 9.761316019001991e-06, "loss": 2.2106, "step": 4380 }, { "epoch": 0.5691418408181413, "grad_norm": 0.7337877154350281, "learning_rate": 9.756699270996848e-06, "loss": 2.2257, "step": 4400 }, { "epoch": 0.5717288491854966, "grad_norm": 0.7337206602096558, "learning_rate": 9.752039412935627e-06, "loss": 2.2066, "step": 4420 }, { "epoch": 0.5743158575528517, "grad_norm": 0.8056983947753906, "learning_rate": 9.74733648705071e-06, "loss": 2.2049, "step": 4440 }, { "epoch": 0.576902865920207, "grad_norm": 0.7203987240791321, "learning_rate": 9.742590535964805e-06, "loss": 2.2279, "step": 4460 }, { "epoch": 0.5794898742875622, "grad_norm": 0.7495117783546448, "learning_rate": 9.737801602690554e-06, "loss": 2.1986, "step": 4480 }, { "epoch": 0.5820768826549173, "grad_norm": 0.7343236207962036, "learning_rate": 9.732969730630153e-06, "loss": 2.2233, "step": 4500 }, { "epoch": 0.5846638910222726, "grad_norm": 0.7727257609367371, "learning_rate": 9.728094963574948e-06, "loss": 2.2042, "step": 4520 }, { "epoch": 0.5872508993896277, "grad_norm": 0.7064406275749207, "learning_rate": 9.723177345705048e-06, "loss": 2.2295, "step": 4540 }, { "epoch": 0.5898379077569829, "grad_norm": 0.7306511998176575, "learning_rate": 9.71821692158892e-06, "loss": 2.1982, "step": 4560 }, { "epoch": 0.5924249161243381, "grad_norm": 0.7717193365097046, "learning_rate": 9.713213736182976e-06, "loss": 2.206, "step": 4580 }, { "epoch": 0.5950119244916933, "grad_norm": 0.7180883288383484, "learning_rate": 9.708167834831183e-06, "loss": 2.2044, "step": 4600 }, { "epoch": 0.5975989328590484, "grad_norm": 0.7017503380775452, "learning_rate": 9.703079263264643e-06, "loss": 2.192, "step": 4620 }, { "epoch": 0.6001859412264037, "grad_norm": 0.7421537637710571, "learning_rate": 9.697948067601176e-06, "loss": 2.199, "step": 4640 }, { "epoch": 0.6027729495937588, "grad_norm": 0.7729679942131042, "learning_rate": 9.692774294344905e-06, "loss": 2.2073, "step": 4660 }, { "epoch": 0.6053599579611141, "grad_norm": 0.7517857551574707, "learning_rate": 9.687557990385836e-06, "loss": 2.1942, "step": 4680 }, { "epoch": 0.6079469663284692, "grad_norm": 0.7258435487747192, "learning_rate": 9.682299202999433e-06, "loss": 2.1916, "step": 4700 }, { "epoch": 0.6105339746958244, "grad_norm": 0.7256997227668762, "learning_rate": 9.676997979846183e-06, "loss": 2.1986, "step": 4720 }, { "epoch": 0.6131209830631796, "grad_norm": 0.7594742774963379, "learning_rate": 9.671654368971176e-06, "loss": 2.1867, "step": 4740 }, { "epoch": 0.6157079914305348, "grad_norm": 0.7546527981758118, "learning_rate": 9.666268418803655e-06, "loss": 2.1999, "step": 4760 }, { "epoch": 0.6182949997978899, "grad_norm": 0.7679339051246643, "learning_rate": 9.660840178156592e-06, "loss": 2.1964, "step": 4780 }, { "epoch": 0.6208820081652452, "grad_norm": 0.7719926834106445, "learning_rate": 9.655369696226235e-06, "loss": 2.1829, "step": 4800 }, { "epoch": 0.6234690165326003, "grad_norm": 0.7456310987472534, "learning_rate": 9.649857022591664e-06, "loss": 2.1725, "step": 4820 }, { "epoch": 0.6260560248999555, "grad_norm": 0.720140814781189, "learning_rate": 9.644302207214346e-06, "loss": 2.1806, "step": 4840 }, { "epoch": 0.6286430332673107, "grad_norm": 0.7672199010848999, "learning_rate": 9.63870530043768e-06, "loss": 2.1921, "step": 4860 }, { "epoch": 0.6312300416346659, "grad_norm": 0.7888000011444092, "learning_rate": 9.633066352986538e-06, "loss": 2.198, "step": 4880 }, { "epoch": 0.6338170500020212, "grad_norm": 0.7024748921394348, "learning_rate": 9.627385415966807e-06, "loss": 2.1579, "step": 4900 }, { "epoch": 0.6364040583693763, "grad_norm": 0.7126362919807434, "learning_rate": 9.62166254086493e-06, "loss": 2.1882, "step": 4920 }, { "epoch": 0.6389910667367315, "grad_norm": 0.6748985052108765, "learning_rate": 9.61589777954743e-06, "loss": 2.1931, "step": 4940 }, { "epoch": 0.6415780751040867, "grad_norm": 0.7744324207305908, "learning_rate": 9.61009118426045e-06, "loss": 2.1823, "step": 4960 }, { "epoch": 0.6441650834714419, "grad_norm": 0.6999046802520752, "learning_rate": 9.604242807629275e-06, "loss": 2.1598, "step": 4980 }, { "epoch": 0.646752091838797, "grad_norm": 0.7126173973083496, "learning_rate": 9.59835270265785e-06, "loss": 2.1661, "step": 5000 }, { "epoch": 0.6493391002061523, "grad_norm": 0.7425235509872437, "learning_rate": 9.592420922728312e-06, "loss": 2.1729, "step": 5020 }, { "epoch": 0.6519261085735074, "grad_norm": 0.735068142414093, "learning_rate": 9.586447521600496e-06, "loss": 2.1734, "step": 5040 }, { "epoch": 0.6545131169408626, "grad_norm": 0.772686779499054, "learning_rate": 9.580432553411446e-06, "loss": 2.1943, "step": 5060 }, { "epoch": 0.6571001253082178, "grad_norm": 0.8012945652008057, "learning_rate": 9.574376072674936e-06, "loss": 2.1678, "step": 5080 }, { "epoch": 0.659687133675573, "grad_norm": 0.7072063684463501, "learning_rate": 9.568278134280966e-06, "loss": 2.1749, "step": 5100 }, { "epoch": 0.6622741420429281, "grad_norm": 0.687140941619873, "learning_rate": 9.562138793495268e-06, "loss": 2.1844, "step": 5120 }, { "epoch": 0.6648611504102834, "grad_norm": 0.7809275984764099, "learning_rate": 9.555958105958805e-06, "loss": 2.1719, "step": 5140 }, { "epoch": 0.6674481587776385, "grad_norm": 0.7361642122268677, "learning_rate": 9.549736127687265e-06, "loss": 2.1706, "step": 5160 }, { "epoch": 0.6700351671449938, "grad_norm": 0.7150685787200928, "learning_rate": 9.543472915070555e-06, "loss": 2.1648, "step": 5180 }, { "epoch": 0.6726221755123489, "grad_norm": 0.7491324543952942, "learning_rate": 9.537168524872292e-06, "loss": 2.156, "step": 5200 }, { "epoch": 0.6752091838797041, "grad_norm": 0.7028157711029053, "learning_rate": 9.530823014229283e-06, "loss": 2.1588, "step": 5220 }, { "epoch": 0.6777961922470593, "grad_norm": 0.7949670553207397, "learning_rate": 9.52443644065101e-06, "loss": 2.1788, "step": 5240 }, { "epoch": 0.6803832006144145, "grad_norm": 0.7003277540206909, "learning_rate": 9.518008862019116e-06, "loss": 2.1917, "step": 5260 }, { "epoch": 0.6829702089817696, "grad_norm": 0.7252909541130066, "learning_rate": 9.511540336586864e-06, "loss": 2.1709, "step": 5280 }, { "epoch": 0.6855572173491249, "grad_norm": 0.7193975448608398, "learning_rate": 9.505030922978626e-06, "loss": 2.185, "step": 5300 }, { "epoch": 0.68814422571648, "grad_norm": 0.7502670288085938, "learning_rate": 9.49848068018934e-06, "loss": 2.1787, "step": 5320 }, { "epoch": 0.6907312340838352, "grad_norm": 0.7460989952087402, "learning_rate": 9.49188966758398e-06, "loss": 2.1557, "step": 5340 }, { "epoch": 0.6933182424511904, "grad_norm": 0.710442066192627, "learning_rate": 9.485257944897021e-06, "loss": 2.1547, "step": 5360 }, { "epoch": 0.6959052508185456, "grad_norm": 0.7363094091415405, "learning_rate": 9.478585572231891e-06, "loss": 2.1473, "step": 5380 }, { "epoch": 0.6984922591859009, "grad_norm": 0.7203119397163391, "learning_rate": 9.47187261006043e-06, "loss": 2.1743, "step": 5400 }, { "epoch": 0.701079267553256, "grad_norm": 0.715248167514801, "learning_rate": 9.465119119222346e-06, "loss": 2.1626, "step": 5420 }, { "epoch": 0.7036662759206112, "grad_norm": 0.7098533511161804, "learning_rate": 9.458325160924648e-06, "loss": 2.1807, "step": 5440 }, { "epoch": 0.7062532842879664, "grad_norm": 0.7714352607727051, "learning_rate": 9.451490796741117e-06, "loss": 2.1517, "step": 5460 }, { "epoch": 0.7088402926553216, "grad_norm": 0.720448911190033, "learning_rate": 9.444616088611718e-06, "loss": 2.1775, "step": 5480 }, { "epoch": 0.7114273010226767, "grad_norm": 0.7580015659332275, "learning_rate": 9.437701098842067e-06, "loss": 2.1529, "step": 5500 }, { "epoch": 0.714014309390032, "grad_norm": 0.727325439453125, "learning_rate": 9.430745890102849e-06, "loss": 2.1654, "step": 5520 }, { "epoch": 0.7166013177573871, "grad_norm": 0.7433022260665894, "learning_rate": 9.423750525429248e-06, "loss": 2.1565, "step": 5540 }, { "epoch": 0.7191883261247423, "grad_norm": 0.728881299495697, "learning_rate": 9.416715068220393e-06, "loss": 2.1734, "step": 5560 }, { "epoch": 0.7217753344920975, "grad_norm": 0.7467840909957886, "learning_rate": 9.409639582238761e-06, "loss": 2.1502, "step": 5580 }, { "epoch": 0.7243623428594527, "grad_norm": 0.7820594310760498, "learning_rate": 9.40252413160962e-06, "loss": 2.1725, "step": 5600 }, { "epoch": 0.7269493512268079, "grad_norm": 0.7077836394309998, "learning_rate": 9.395368780820433e-06, "loss": 2.1508, "step": 5620 }, { "epoch": 0.7295363595941631, "grad_norm": 0.7221850752830505, "learning_rate": 9.388173594720283e-06, "loss": 2.1649, "step": 5640 }, { "epoch": 0.7321233679615182, "grad_norm": 0.7874971628189087, "learning_rate": 9.380938638519274e-06, "loss": 2.158, "step": 5660 }, { "epoch": 0.7347103763288735, "grad_norm": 0.7347155213356018, "learning_rate": 9.373663977787956e-06, "loss": 2.1486, "step": 5680 }, { "epoch": 0.7372973846962286, "grad_norm": 0.7876786589622498, "learning_rate": 9.366349678456717e-06, "loss": 2.1501, "step": 5700 }, { "epoch": 0.7398843930635838, "grad_norm": 0.678352952003479, "learning_rate": 9.35899580681519e-06, "loss": 2.1644, "step": 5720 }, { "epoch": 0.742471401430939, "grad_norm": 0.7279735803604126, "learning_rate": 9.351602429511655e-06, "loss": 2.1508, "step": 5740 }, { "epoch": 0.7450584097982942, "grad_norm": 0.7041738629341125, "learning_rate": 9.344169613552428e-06, "loss": 2.1617, "step": 5760 }, { "epoch": 0.7476454181656493, "grad_norm": 0.750642716884613, "learning_rate": 9.336697426301267e-06, "loss": 2.1409, "step": 5780 }, { "epoch": 0.7502324265330046, "grad_norm": 0.7688580751419067, "learning_rate": 9.329185935478741e-06, "loss": 2.1459, "step": 5800 }, { "epoch": 0.7528194349003597, "grad_norm": 0.704578697681427, "learning_rate": 9.321635209161642e-06, "loss": 2.1417, "step": 5820 }, { "epoch": 0.7554064432677149, "grad_norm": 0.733323872089386, "learning_rate": 9.314045315782339e-06, "loss": 2.1516, "step": 5840 }, { "epoch": 0.7579934516350701, "grad_norm": 0.771930992603302, "learning_rate": 9.306416324128184e-06, "loss": 2.1256, "step": 5860 }, { "epoch": 0.7605804600024253, "grad_norm": 0.6910899877548218, "learning_rate": 9.298748303340871e-06, "loss": 2.1421, "step": 5880 }, { "epoch": 0.7631674683697806, "grad_norm": 0.7119818329811096, "learning_rate": 9.291041322915824e-06, "loss": 2.1631, "step": 5900 }, { "epoch": 0.7657544767371357, "grad_norm": 0.6817770600318909, "learning_rate": 9.283295452701549e-06, "loss": 2.143, "step": 5920 }, { "epoch": 0.7683414851044909, "grad_norm": 0.714541494846344, "learning_rate": 9.275510762899016e-06, "loss": 2.1546, "step": 5940 }, { "epoch": 0.7709284934718461, "grad_norm": 0.6969371438026428, "learning_rate": 9.267687324061016e-06, "loss": 2.1186, "step": 5960 }, { "epoch": 0.7735155018392013, "grad_norm": 0.7325617671012878, "learning_rate": 9.259825207091526e-06, "loss": 2.1363, "step": 5980 }, { "epoch": 0.7761025102065564, "grad_norm": 0.743165135383606, "learning_rate": 9.25192448324506e-06, "loss": 2.1269, "step": 6000 }, { "epoch": 0.7786895185739117, "grad_norm": 0.7538695931434631, "learning_rate": 9.243985224126031e-06, "loss": 2.1237, "step": 6020 }, { "epoch": 0.7812765269412668, "grad_norm": 0.7549970746040344, "learning_rate": 9.236007501688094e-06, "loss": 2.1343, "step": 6040 }, { "epoch": 0.783863535308622, "grad_norm": 0.732627272605896, "learning_rate": 9.2279913882335e-06, "loss": 2.1465, "step": 6060 }, { "epoch": 0.7864505436759772, "grad_norm": 0.7083766460418701, "learning_rate": 9.219936956412436e-06, "loss": 2.1394, "step": 6080 }, { "epoch": 0.7890375520433324, "grad_norm": 0.7239031195640564, "learning_rate": 9.211844279222376e-06, "loss": 2.1386, "step": 6100 }, { "epoch": 0.7916245604106876, "grad_norm": 0.7016878128051758, "learning_rate": 9.2037134300074e-06, "loss": 2.1313, "step": 6120 }, { "epoch": 0.7942115687780428, "grad_norm": 0.6846844553947449, "learning_rate": 9.195544482457555e-06, "loss": 2.1383, "step": 6140 }, { "epoch": 0.7967985771453979, "grad_norm": 0.7442426085472107, "learning_rate": 9.187337510608168e-06, "loss": 2.1177, "step": 6160 }, { "epoch": 0.7993855855127532, "grad_norm": 0.7443544268608093, "learning_rate": 9.179092588839178e-06, "loss": 2.1391, "step": 6180 }, { "epoch": 0.8019725938801083, "grad_norm": 0.7053080201148987, "learning_rate": 9.170809791874468e-06, "loss": 2.1221, "step": 6200 }, { "epoch": 0.8045596022474635, "grad_norm": 0.7665020227432251, "learning_rate": 9.16248919478119e-06, "loss": 2.1116, "step": 6220 }, { "epoch": 0.8071466106148187, "grad_norm": 0.7906709909439087, "learning_rate": 9.154130872969067e-06, "loss": 2.1363, "step": 6240 }, { "epoch": 0.8097336189821739, "grad_norm": 0.6853694915771484, "learning_rate": 9.145734902189733e-06, "loss": 2.149, "step": 6260 }, { "epoch": 0.812320627349529, "grad_norm": 0.7411865592002869, "learning_rate": 9.137301358536032e-06, "loss": 2.1355, "step": 6280 }, { "epoch": 0.8149076357168843, "grad_norm": 0.8013186454772949, "learning_rate": 9.128830318441327e-06, "loss": 2.1175, "step": 6300 }, { "epoch": 0.8174946440842394, "grad_norm": 0.7919278144836426, "learning_rate": 9.120321858678817e-06, "loss": 2.128, "step": 6320 }, { "epoch": 0.8200816524515947, "grad_norm": 0.7355955243110657, "learning_rate": 9.111776056360838e-06, "loss": 2.1253, "step": 6340 }, { "epoch": 0.8226686608189498, "grad_norm": 0.7750183343887329, "learning_rate": 9.103192988938155e-06, "loss": 2.1225, "step": 6360 }, { "epoch": 0.825255669186305, "grad_norm": 0.7022154927253723, "learning_rate": 9.094572734199271e-06, "loss": 2.1193, "step": 6380 }, { "epoch": 0.8278426775536603, "grad_norm": 0.7672535181045532, "learning_rate": 9.085915370269723e-06, "loss": 2.1188, "step": 6400 }, { "epoch": 0.8304296859210154, "grad_norm": 0.7107143998146057, "learning_rate": 9.077220975611363e-06, "loss": 2.1278, "step": 6420 }, { "epoch": 0.8330166942883706, "grad_norm": 0.7380732297897339, "learning_rate": 9.068489629021655e-06, "loss": 2.1374, "step": 6440 }, { "epoch": 0.8356037026557258, "grad_norm": 0.6959198117256165, "learning_rate": 9.05972140963296e-06, "loss": 2.129, "step": 6460 }, { "epoch": 0.838190711023081, "grad_norm": 0.742127001285553, "learning_rate": 9.050916396911818e-06, "loss": 2.1285, "step": 6480 }, { "epoch": 0.8407777193904361, "grad_norm": 0.6720155477523804, "learning_rate": 9.042074670658223e-06, "loss": 2.1172, "step": 6500 }, { "epoch": 0.8433647277577914, "grad_norm": 0.7020736932754517, "learning_rate": 9.033196311004915e-06, "loss": 2.1036, "step": 6520 }, { "epoch": 0.8459517361251465, "grad_norm": 0.746281087398529, "learning_rate": 9.024281398416632e-06, "loss": 2.1183, "step": 6540 }, { "epoch": 0.8485387444925018, "grad_norm": 0.7673128843307495, "learning_rate": 9.015330013689396e-06, "loss": 2.1435, "step": 6560 }, { "epoch": 0.8511257528598569, "grad_norm": 0.7635971903800964, "learning_rate": 9.006342237949782e-06, "loss": 2.1018, "step": 6580 }, { "epoch": 0.8537127612272121, "grad_norm": 0.7365761995315552, "learning_rate": 8.997318152654167e-06, "loss": 2.116, "step": 6600 }, { "epoch": 0.8562997695945673, "grad_norm": 0.7582866549491882, "learning_rate": 8.988257839588011e-06, "loss": 2.1146, "step": 6620 }, { "epoch": 0.8588867779619225, "grad_norm": 0.7569854259490967, "learning_rate": 8.979161380865104e-06, "loss": 2.1156, "step": 6640 }, { "epoch": 0.8614737863292776, "grad_norm": 0.6821621656417847, "learning_rate": 8.970028858926825e-06, "loss": 2.1134, "step": 6660 }, { "epoch": 0.8640607946966329, "grad_norm": 0.7307649850845337, "learning_rate": 8.96086035654139e-06, "loss": 2.124, "step": 6680 }, { "epoch": 0.866647803063988, "grad_norm": 0.7775338292121887, "learning_rate": 8.951655956803118e-06, "loss": 2.1052, "step": 6700 }, { "epoch": 0.8692348114313432, "grad_norm": 0.7425001859664917, "learning_rate": 8.942415743131651e-06, "loss": 2.106, "step": 6720 }, { "epoch": 0.8718218197986984, "grad_norm": 0.7379507422447205, "learning_rate": 8.933139799271229e-06, "loss": 2.0974, "step": 6740 }, { "epoch": 0.8744088281660536, "grad_norm": 0.7932276129722595, "learning_rate": 8.923828209289904e-06, "loss": 2.1257, "step": 6760 }, { "epoch": 0.8769958365334087, "grad_norm": 0.7237013578414917, "learning_rate": 8.914481057578791e-06, "loss": 2.1033, "step": 6780 }, { "epoch": 0.879582844900764, "grad_norm": 0.7310687899589539, "learning_rate": 8.905098428851309e-06, "loss": 2.1194, "step": 6800 }, { "epoch": 0.8821698532681191, "grad_norm": 0.6933685541152954, "learning_rate": 8.8956804081424e-06, "loss": 2.0891, "step": 6820 }, { "epoch": 0.8847568616354744, "grad_norm": 0.7352440357208252, "learning_rate": 8.886227080807762e-06, "loss": 2.1022, "step": 6840 }, { "epoch": 0.8873438700028295, "grad_norm": 0.7073638439178467, "learning_rate": 8.876738532523081e-06, "loss": 2.1065, "step": 6860 }, { "epoch": 0.8899308783701847, "grad_norm": 0.7440693974494934, "learning_rate": 8.867214849283252e-06, "loss": 2.1079, "step": 6880 }, { "epoch": 0.89251788673754, "grad_norm": 0.7651025056838989, "learning_rate": 8.8576561174016e-06, "loss": 2.121, "step": 6900 }, { "epoch": 0.8951048951048951, "grad_norm": 0.7150782346725464, "learning_rate": 8.84806242350909e-06, "loss": 2.1025, "step": 6920 }, { "epoch": 0.8976919034722503, "grad_norm": 0.7346411943435669, "learning_rate": 8.838433854553555e-06, "loss": 2.0959, "step": 6940 }, { "epoch": 0.9002789118396055, "grad_norm": 0.7531387209892273, "learning_rate": 8.828770497798897e-06, "loss": 2.0901, "step": 6960 }, { "epoch": 0.9028659202069607, "grad_norm": 0.7870126366615295, "learning_rate": 8.819072440824303e-06, "loss": 2.1034, "step": 6980 }, { "epoch": 0.9054529285743158, "grad_norm": 0.7796097993850708, "learning_rate": 8.80933977152345e-06, "loss": 2.0825, "step": 7000 }, { "epoch": 0.9080399369416711, "grad_norm": 0.7178963422775269, "learning_rate": 8.799572578103703e-06, "loss": 2.1252, "step": 7020 }, { "epoch": 0.9106269453090262, "grad_norm": 0.7850649952888489, "learning_rate": 8.789770949085321e-06, "loss": 2.0886, "step": 7040 }, { "epoch": 0.9132139536763815, "grad_norm": 0.7312331795692444, "learning_rate": 8.779934973300657e-06, "loss": 2.1015, "step": 7060 }, { "epoch": 0.9158009620437366, "grad_norm": 0.7429481148719788, "learning_rate": 8.770064739893346e-06, "loss": 2.0791, "step": 7080 }, { "epoch": 0.9183879704110918, "grad_norm": 0.70722895860672, "learning_rate": 8.7601603383175e-06, "loss": 2.0992, "step": 7100 }, { "epoch": 0.920974978778447, "grad_norm": 0.7041098475456238, "learning_rate": 8.750221858336902e-06, "loss": 2.1027, "step": 7120 }, { "epoch": 0.9235619871458022, "grad_norm": 0.7348500490188599, "learning_rate": 8.740249390024183e-06, "loss": 2.0899, "step": 7140 }, { "epoch": 0.9261489955131573, "grad_norm": 0.7186647653579712, "learning_rate": 8.730243023760012e-06, "loss": 2.1059, "step": 7160 }, { "epoch": 0.9287360038805126, "grad_norm": 0.7586842775344849, "learning_rate": 8.720202850232281e-06, "loss": 2.0929, "step": 7180 }, { "epoch": 0.9313230122478677, "grad_norm": 0.7751206159591675, "learning_rate": 8.710128960435271e-06, "loss": 2.0961, "step": 7200 }, { "epoch": 0.9339100206152229, "grad_norm": 0.7438105344772339, "learning_rate": 8.700021445668839e-06, "loss": 2.1013, "step": 7220 }, { "epoch": 0.9364970289825781, "grad_norm": 0.7343020439147949, "learning_rate": 8.68988039753758e-06, "loss": 2.0904, "step": 7240 }, { "epoch": 0.9390840373499333, "grad_norm": 0.7382264733314514, "learning_rate": 8.67970590795001e-06, "loss": 2.1016, "step": 7260 }, { "epoch": 0.9416710457172885, "grad_norm": 0.720942497253418, "learning_rate": 8.669498069117721e-06, "loss": 2.1167, "step": 7280 }, { "epoch": 0.9442580540846437, "grad_norm": 0.7112380266189575, "learning_rate": 8.65925697355455e-06, "loss": 2.0981, "step": 7300 }, { "epoch": 0.9468450624519988, "grad_norm": 0.7193992137908936, "learning_rate": 8.648982714075743e-06, "loss": 2.0853, "step": 7320 }, { "epoch": 0.9494320708193541, "grad_norm": 0.7250093221664429, "learning_rate": 8.638675383797106e-06, "loss": 2.0936, "step": 7340 }, { "epoch": 0.9520190791867092, "grad_norm": 0.727990448474884, "learning_rate": 8.628335076134173e-06, "loss": 2.0882, "step": 7360 }, { "epoch": 0.9546060875540644, "grad_norm": 0.7733245491981506, "learning_rate": 8.617961884801346e-06, "loss": 2.0799, "step": 7380 }, { "epoch": 0.9571930959214197, "grad_norm": 0.7614827752113342, "learning_rate": 8.60755590381106e-06, "loss": 2.0935, "step": 7400 }, { "epoch": 0.9597801042887748, "grad_norm": 0.7480348348617554, "learning_rate": 8.597117227472915e-06, "loss": 2.0889, "step": 7420 }, { "epoch": 0.96236711265613, "grad_norm": 0.7127954959869385, "learning_rate": 8.586645950392835e-06, "loss": 2.0981, "step": 7440 }, { "epoch": 0.9649541210234852, "grad_norm": 0.6996986865997314, "learning_rate": 8.576142167472204e-06, "loss": 2.0856, "step": 7460 }, { "epoch": 0.9675411293908404, "grad_norm": 0.757079005241394, "learning_rate": 8.565605973907006e-06, "loss": 2.0873, "step": 7480 }, { "epoch": 0.9701281377581955, "grad_norm": 0.7550200819969177, "learning_rate": 8.555037465186962e-06, "loss": 2.0817, "step": 7500 }, { "epoch": 0.9727151461255508, "grad_norm": 0.7152219414710999, "learning_rate": 8.544436737094672e-06, "loss": 2.0962, "step": 7520 }, { "epoch": 0.9753021544929059, "grad_norm": 0.774013876914978, "learning_rate": 8.533803885704732e-06, "loss": 2.0944, "step": 7540 }, { "epoch": 0.9778891628602612, "grad_norm": 0.721843421459198, "learning_rate": 8.523139007382881e-06, "loss": 2.0849, "step": 7560 }, { "epoch": 0.9804761712276163, "grad_norm": 0.7735098600387573, "learning_rate": 8.51244219878511e-06, "loss": 2.0906, "step": 7580 }, { "epoch": 0.9830631795949715, "grad_norm": 0.7077389359474182, "learning_rate": 8.501713556856803e-06, "loss": 2.0665, "step": 7600 }, { "epoch": 0.9856501879623267, "grad_norm": 0.7230038046836853, "learning_rate": 8.490953178831846e-06, "loss": 2.0766, "step": 7620 }, { "epoch": 0.9882371963296819, "grad_norm": 0.7460753321647644, "learning_rate": 8.480161162231747e-06, "loss": 2.0556, "step": 7640 }, { "epoch": 0.990824204697037, "grad_norm": 0.7653132081031799, "learning_rate": 8.469337604864759e-06, "loss": 2.0821, "step": 7660 }, { "epoch": 0.9934112130643923, "grad_norm": 0.7243251204490662, "learning_rate": 8.458482604824988e-06, "loss": 2.0926, "step": 7680 }, { "epoch": 0.9959982214317474, "grad_norm": 0.7776849865913391, "learning_rate": 8.447596260491508e-06, "loss": 2.0925, "step": 7700 }, { "epoch": 0.9985852297991026, "grad_norm": 0.7500579953193665, "learning_rate": 8.436678670527463e-06, "loss": 2.0736, "step": 7720 } ], "logging_steps": 20, "max_steps": 23190, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.963409237367639e+19, "train_batch_size": 12, "trial_name": null, "trial_params": null }